首页    期刊浏览 2024年11月28日 星期四
登录注册

文章基本信息

  • 标题:Gait Recognition by Fusing Direct Cross-view Matching Scores for Criminal Investigation
  • 本地全文:下载
  • 作者:Daigo Muramatsu ; Yasushi Makihara ; Yasushi Yagi
  • 期刊名称:Information and Media Technologies
  • 电子版ISSN:1881-0896
  • 出版年度:2013
  • 卷号:8
  • 期号:4
  • 页码:1026-1030
  • DOI:10.11185/imt.8.1026
  • 出版社:Information and Media Technologies Editorial Board
  • 摘要:

    We focus on gait recognition for criminal investigation. In criminal investigation, person authentication is performed by comparing target data at the crime scene and multiple gait data with slightly different views from that of the target data. For this task, we propose fusion of direct cross-view matching. Cross-view matching generally produces worse result than those of same-view matching when view-variant features are used. However, the correlation between cross-view matching with different view pairs is low and it provides improved accuracy. Experimental results performed utilizing large-scale dataset under settings resembling actual criminal investigation cases, show that the proposed approach works well.

  • 关键词:gait recognition; criminal investication; cross-view; fusion; biometrics
国家哲学社会科学文献中心版权所有